Adaptive RAG

RAG: Retrieval-Augmented Generation

Ask about this topic

Overview

Adaptive RAG studies how language models can decide whether external evidence is needed, which sources or retrieval methods to use, and when to stop gathering information. Systems use signals such as confidence, evidence sufficiency, query complexity, or reasoning gaps to route queries, refine searches, verify evidence, and allocate retrieval or token budgets. Approaches range from training-free controllers and confidence gates to learned policies, retriever portfolios, and retrieval decisions integrated into generation; they are tested on question answering, multi-hop reasoning, long documents, and specialized domains. The central challenge is balancing answer quality and reliability against latency and cost, since retrieval can add noise, and policies that work well on one model, query type, or dataset may not transfer or remain robust to query variations.

Latest papers

CardsList

59 papers6 papers in the last four weeks, down 33% on the four weeks before. 0.0% of all new papers.

  1. Adaptive Retrieval, Selective Answers: Evaluating Conformal Factuality in Agentic RAG

    Oct 26, 2026Muhammad Aimal Rehman, Chi-Kuang YehRAG EvaluationAgentic RAG

    Department of Mathematics & Statistics, Georgia State University, Atlanta, GA, USA

  2. MAPS: Macro-Adaptive Parallel Reasoning for Regulating Search Momentum in Retrieval-Augmented Generation

    Oct 21, 2026Xinze Li, Dingwen Zhang, Zhenghao Liu +5Retrieval-Augmented GenerationIterative RAG

    School of Computer Science and Engineering, Northeastern University, Shenyang, China · Department of Computer Science and Technology, Tsinghua University, Beijing, China

  3. Retrieve What Helps, Only When It Helps: Agentic Reinforcement Learning for Selective Retrieval-Augmented Machine Translation

    Oct 14, 2026Shijun Li, Yang Liu, Najmeh Sadoughi +5Machine TranslationRetrieval-Augmented Generation

    The University of Texas at Austin · Amazon

  4. ARMED: Adaptive Retrieval-Augmented Medication Recommendation

    Oct 12, 2026Kyungkeon Chung, Se Un Park, Hyejin Lee +1Medication RecommendationAdaptive RAG

    UX Factory, Inc., Seongnam-si, South Korea

  5. Fast and Accurate: Improving Personalized LLM Performance by Semantic Concentration Inspired Workload Split between RAG and Fine-Tuning

    Oct 11, 2026Xingke Yang, Sicong Li, Lingfeng Yao +4Personalized Language ModelsLLM Inference Efficiency

    University of Houston, USA · Independent Researcher, USA

  6. Look Before You Leap: Thermodynamic Arbitration of Parametric and Non-Parametric Knowledge in LLM Agents via Self-Regulating Memory Architectures

    Oct 4, 2026Akash Das, Ishan RoyCognitive Architectures for AI AgentsAdaptive RAG

    Fidelity Investments

  7. BELIEFRAG: Making Adaptive RAG State-Aware under Evolving Evidence

    Sep 30, 2026Hongji PuAdaptive RAGEvidence Selection

    University of Illinois Urbana-Champaign

  8. Return or Revise? Learning When Revision Helps Retrieval-Augmented QA

    Sep 24, 2026Nicholas Kashani Motlagh, Tim Anderson, Jeremy Gwinnup +1Retrieval-Augmented GenerationLLM Answer Verification

    DCS Corp · Air Force Research Laboratory

  9. REAT: A Reflective Experience-Augmented Tutoring Framework for Multi-turn Mathematical Instruction

    Sep 24, 2026Jianheng Zhou, Chaoli Zhang, Xingjun Wei +6Intelligent Tutoring SystemsAdaptive RAG

    School of Electrical and Electronic Engineering, Nanyang Technological University · Zhejiang Normal University · Telfer School of Management, University of Ottawa +5

  10. One Size Does Not Fit All! Dynamic Retriever and Generator Selection for RAG

    Sep 15, 2026Neeraj Anand, Payel Santra, Partha Basuchowdhuri +2Retrieval-Augmented GenerationAdaptive RAG

    Media and Data Science Research Lab Adobe Systems, Noida, India · IACS Kolkata, India · University of Glasgow Glasgow, United Kingdom

  11. ORDER: Task-Conditioned Routing for Retrieval-Augmented Generation

    Sep 15, 2026Aurélien Pellet, Julien Perez, Marie PurenRetrieval-Augmented GenerationAdaptive RAG

    LRE · LRE, EPITA · EPITECH +2

  12. CWM: Controllable White-Box Meta-Prompting for Adaptive Retrieval-Augmented Generation and Reasoning Ability

    Sep 14, 2026Keuntae Kim, Eunhye Jeong, Yong Suk ChoiLLM PromptingAdaptive RAG

    Department of Computer Science, Hanyang University, Seoul, Korea · Department of Artificial Intelligence, Hanyang University, Seoul, Korea

  13. VikingRAG: Accurate and Token-efficient Retrieval-augmented Generation over Structured Documents

    Sep 10, 2026Peiyuan Gao, Gaoyuan Zhang, Haojie Qin +5Retrieval-Augmented GenerationStructured RAG

    Renmin University of China · Independent Researcher · Fudan University

  14. Better Together: Complementary Query Rewriting Under a Strong RAG Baseline

    Sep 4, 2026Sara Shanian, Xiaoqin Yi, Pavlo Ruban +1Retrieval-Augmented GenerationAdaptive RAG

    ServiceNow

  15. NE-R1: Enhancing Named Entity Recognition Model via Reinforcement Learning

    Sep 2, 2026Meixuan Chen, Hehan Li, Ruizhi Zhao +8Named Entity RecognitionAdaptive RAG

    Shenzhen Graduate School, Peking University · Baidu, Inc., Beijing, China · Shenzhen University, Shenzhen, China +3

  16. Adaptive Critical Token-Aware Retrieval for Repository-Level Code Generation

    Sep 1, 2026Kefeng Duan, Dewu Zheng, Yanlin Wang +8Retrieval-Augmented GenerationAdaptive RAG

    Sun Yat-sen University, Guangzhou 510006, P.R. China · Huawei Cloud Computing Technologies Co., Ltd.

  17. hoBIT: A Profile-Aware Retrieval-Augmented Chatbot for University Academic Advising

    Aug 27, 2026Yoonseo Kim, Seongmin Lee, Joongheon Kim +1Adaptive RAGConversational Agents

    Korea University Seoul, Korea

  18. Less can be More: Relieving RAG Bottlenecks via Evidence Frontloading and Pressure-Adaptive Budgeting

    Aug 25, 2026Weibin Cai, Reza ZafaraniRetrieval-Augmented GenerationAdaptive RAG

    Data Lab, EECS Department Syracuse University Syracuse, NY, USA

  19. The Laws of Context Allocation: Causal Measurement and Closed-Loop Orchestration in Generative Search

    Aug 24, 2026Peiyang Liu, Xi Wang, Di Liang +1Iterative RAGRetrieval-Augmented Generation

    National Engineering Research Center for Software Engineering, Peking University, China · Peking University, China · Tencent, China

  20. When Should Multi-Round RAG Stop? Structured Stopping Judgments and Retrieval Reduction in Search-R1

    Aug 13, 2026Weimeng LuoAdaptive RAGRAG Evaluation

    Unaffiliated

  21. AdaMem: Adaptive Memory Token Allocation for Soft Compression in Retrieval-Augmented Generation

    Aug 12, 2026Artem Sakhno, Grigorii Davydenko, Omar Zoloev +3RAG Context CompressionContext Compression

  22. SAGE: SLO-Aware Adaptive Retrieval for Production RAG Systems

    Aug 8, 2026Muhammad Faizan Raza, Shuo, Yang +1Retrieval-Augmented GenerationAdaptive RAG

    Luna · Engineering Pennsylvania State University Great Valley Malvern, PA, USA · Business Division Pennsylvania State University Brandywine Media, PA, USA

  23. D2^2F-ReAG: Dynamic Decomposition and Filtering for Multi-Hop Reasoning-Augmented Generation

    Aug 5, 2026Jiaoyang Li, Junhao Ruan, Shengwei Tang +4Multi-Hop QARetrieval-Augmented Generation

    Northeastern University, Shenyang, China · Kunming University of Science and Technology, Kunming, China · NiuTrans Research, Shenyang, China

  24. MEGRAG: Multi-Granular Evidence Graphs for Answer-Aware Multi-Hop RAG

    Aug 3, 2026Weidong Bao, Yingying Sun, Jun Yang +7Multi-Hop QARetrieval-Augmented Generation

    Northeastern University, Shenyang, China

  25. CoEvo-Mem: Co-Evolving Retrieval Policy and Memory Bank for LLM Agents

    Aug 3, 2026Bowen Ye, Yongchao Xu, Zhijian Li +3Continual Learning for LLM AgentsAdaptive RAG

    Alibaba Group, Hangzhou, China · School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai 200240, China · University of Science and Technology of China, Hefei, China

  26. ACE-GraphRAG: Agentic Context Engineering for Hierarchical GraphRAG

    Aug 2, 2026Yongfeng Huang, Yuren Lai, Ruiying Chen +3Multi-Hop QAGraph Retrieval-Augmented Generation

    CSE, The Chinese University of Hong Kong · Wuhan University of Technology · The Hong Kong University of Science and Technology +1

  27. TAP-RAG: Task-Aware Policy Control for Long-Document Multimodal Question Answering

    Jul 21, 2026Zhong Ji, Keqi Jin, Yan Zhang +1Multimodal RAGRetrieval-Augmented Generation

    School of Electrical and Information Engineering, Tianjin University · The International Joint Institute of Tianjin University, Fuzhou, Tianjin University · Department of Automation, Tsinghua University

  28. GRASP: GRanularity-Aware Search Policy for Agentic RAG

    Jul 11, 2026Varun Gandhi, Jaewook Lee, Shantanu Todmal +4Multi-Hop QARetrieval-Augmented Generation

    University of Massachusetts Amherst · Adobe Research

  29. Know Before You Fetch: Calibrated Retrieval-Budget Allocation for Retrieval-Augmented Generation

    Jun 29, 2026Zhe Dong, Fang Qin, Manish Shah +1Retrieval-Augmented GenerationSelective Prediction

    University of Maine at Presque Isle · Stanford University · Independent Researcher

  30. ARMOR: Adaptive Retriever Optimization for Low-Resource Telecom Question Answering

    Jun 29, 2026Heshan Fernando, Quan Xiao, Yan Xin +1Retrieval-Augmented GenerationAdaptive RAG

    1Rensselaer Polytechnic Institute, Troy, NY · 2Cornell University, New York, NY · 3Samsung Research America, Berkeley Heights, NJ